#np.random.shuffle(x)
#np.random.shuffle(y)
x = x[perm]
y = y[perm]
val_x = x[-100:]
val_y = y[-100:]
in_x = x[:-200]
in_y = y[:-200]
cross_val_x = x[-200:-100]
cross_val_y = y[-200:-100]
print('population_count: ' + str(population_count))
print('population_size: ' + str(population_size))
print('node_cap: ' + str(node_cap))
print('generations: ' + str(generations))
print('target_accuracy: {}%'.format(target_accuracy * 100))
print('random_seed: ' + str(r))
best_network = evm.evolve_node_count(in_x, in_y, val_x, val_y,
utils.jit_round_compare,
population_count, population_size,
node_cap, generations,
target_accuracy, r)
print(
best_network.validate(cross_val_x, cross_val_y,
utils.jit_round_compare))
utils.display_network(best_network, "wisconsin-breast-cancer")
x = np.array([[1, 0] if rand < 0.25 else
[0, 1] if rand < 0.5 else [1, 1] if rand < 0.75 else [0, 0]
for rand in np.random.random(60000)],
dtype=int)
y = np.array([[
1,
] if np.sum(itm) == 1 else [
0,
] for itm in x],
dtype=int)
# Grab input from the user and print it to stdout
population_count = int(input('population_count: '))
print('{}'.format(population_count))
population_size = int(input('poplation_size: '))
print('{}'.format(population_size))
node_cap = int(input('node_cap: '))
print('{}'.format(node_cap))
generations = int(input('generations: '))
print('{}'.format(generations))
target_accuracy = float(input('target_accuracy: '))
print('{}%'.format(target_accuracy * 100))
r = int(input("random_seed: "))
print(str(r))
for i in range(50):
best_xor = evm.evolve_node_count(x, y, x, y, utils.jit_round_compare,
population_count, population_size,
node_cap, generations,
target_accuracy, i * r + r)
print(population_size)
node_cap = int(input('node_cap: '))
print(node_cap)
generations = int(input('generations: '))
print(generations)
target_accuracy = float(input('target_accuracy: '))
print('{}%'.format(target_accuracy*100))
r = float(input('random_number: '))
print(r)
x = (np.random.random(50000)*2*np.math.pi).reshape(50000, 1)
y = (np.sin(x)+1).reshape(50000, 1)
val_x = (np.random.random(1000)*2*np.math.pi).reshape(1000, 1)
val_y = (np.sin(val_x)+1).reshape(1000, 1)
network = evolutionary_module.evolve_node_count(x, y, val_x, val_y, utils.jit_near_compare, population_count, population_size, node_cap, generations, target_accuracy, r)
# with utils.OutSplit('cos-50k'.format(d= datetime.datetime.now())):
# print('population_count: ' + str(population_count))
# print('population_size: ' + str(population_size))
# print('node_cap: ' + str(node_cap))
# print('generations: ' + str(generations))
# print('target_accuracy: {}%'.format(target_accuracy*100))
# print('random_number: ' + str(r))
# x = (np.random.random(50000)*2*np.math.pi).reshape(50000, 1)
# y = (np.cos(x)+1).reshape(50000, 1)
# val_x = (np.random.random(1000)*2*np.math.pi).reshape(1000, 1)
# val_y = (np.cos(val_x)+1).reshape(1000, 1)
# Grab input from the user and print it to stdout
population_count = int(input('population_count: '))
print('{}'.format(population_count))
population_size = int(input('poplation_size: '))
print('{}'.format(population_size))
node_cap = int(input('node_cap: '))
print('{}'.format(node_cap))
generations = int(input('generations: '))
print('{}'.format(generations))
target_accuracy = float(input('target_accuracy: '))
print('{}%'.format(target_accuracy*100))
r = int(input("random_seed: "))
print(str(r))
for i in range(50):
best = evm.evolve_node_count(x, y, val_x, val_y, utils.jit_near_compare, population_count, population_size, node_cap, generations, target_accuracy, i*r+r)
with utils.OutSplit('nultiple_cos'.format(d= datetime.datetime.now())):
print('population_count: ' + str(population_count))
print('population_size: ' + str(population_size))
print('node_cap: ' + str(node_cap))
print('generations: ' + str(generations))
print('target_accuracy: {}%'.format(target_accuracy*100))
print('random_number: ' + str(r))
x = (np.random.random(50000)*2*np.math.pi).reshape(50000, 1)
y = (np.cos(x)+1).reshape(50000, 1)
val_x = (np.random.random(1000)*2*np.math.pi).reshape(1000, 1)
val_y = (np.cos(val_x)+1).reshape(1000, 1)
train_labels = utils.jit_to_categorical(
mnist_io.labels_from_file(
os.path.join(dataset,
"train-labels-idx1-ubyte\\train-labels.idx1-ubyte"),
60000), 10)
test_images = mnist_io.images_from_file(
os.path.join(dataset, "t10k-images-idx3-ubyte\\t10k-images.idx3-ubyte"),
10000)
test_images = test_images.reshape(10000, 784).astype('float32')
test_images /= 255
test_labels = utils.jit_to_categorical(
mnist_io.labels_from_file(
os.path.join(dataset, "t10k-labels-idx1-ubyte/t10k-labels.idx1-ubyte"),
10000), 10)
with utils.OutSplit('mnist_evolution'):
evolved_network = evolve_node_count(train_images,
train_labels,
test_images,
test_labels,
utils.jit_categorical_compare,
population_count=10,
population_size=15,
node_cap=1500,
generations=50,
target_accuracy=0.95,
r=4)
print(evolved_network.connections, "\n", evolved_network.weights, "\n",
evolved_network.learning_rate)